053613 VU Introduction to Machine Learning (2025W)
Prüfungsimmanente Lehrveranstaltung
Labels
An/Abmeldung
Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").
- Anmeldung von Fr 12.09.2025 09:00 bis Mo 22.09.2025 09:00
- Abmeldung bis Di 14.10.2025 23:59
Details
max. 25 Teilnehmer*innen
Sprache: Englisch
Lehrende
Termine (iCal) - nächster Termin ist mit N markiert
- Donnerstag 02.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 06.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 09.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 13.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 16.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 20.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 23.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 27.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 30.10. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 03.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 06.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 10.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 13.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 17.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 20.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 24.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 27.11. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 01.12. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 04.12. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- N Donnerstag 11.12. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 15.12. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 18.12. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 08.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 12.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 15.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 19.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 22.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Montag 26.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
- Donnerstag 29.01. 15:00 - 16:30 Hörsaal 2, Währinger Straße 29 2.OG
Information
Ziele, Inhalte und Methode der Lehrveranstaltung
Art der Leistungskontrolle und erlaubte Hilfsmittel
* Written exams: in the middle and at the end of the semester; you will be allowed to bring 2 handwritten A4 sheets (4 pages) of notes to each exam* Programming assignments:
(a) Solve machine learning-related tasks in Python at home; you will have to submit your executable source code & a written report on your implementation and results; you can work in small groups but must specify who did what and be able to explain all of the submitted code and all of the submitted report
(b) Present and discuss your implementation and results with your peers in two in-person sessions* Pen & paper exercises: Solve pen & paper exercises at home; to be awarded credits for your solutions you have to present your solutions in the pen & paper exercises sessions (you will be randomly selected)
(a) Solve machine learning-related tasks in Python at home; you will have to submit your executable source code & a written report on your implementation and results; you can work in small groups but must specify who did what and be able to explain all of the submitted code and all of the submitted report
(b) Present and discuss your implementation and results with your peers in two in-person sessions* Pen & paper exercises: Solve pen & paper exercises at home; to be awarded credits for your solutions you have to present your solutions in the pen & paper exercises sessions (you will be randomly selected)
Mindestanforderungen und Beurteilungsmaßstab
Your grade will depend on your performance on the written exams, the programming exercises, and the pen & paper exercises according to the following weighting:
50% Written exams
25% Programming exercises
25% Pen & paper exercisesIn particular, let P = Average weighted percentage on the written exams, the programming exercises, and the pen & paper exercises. Then your grade (if you fulfill the passing criteria) is given as:90% <= P <= 100% Sehr Gut (1)
77% <= P < 90% Gut (2)
62% <= P < 77% Befriedigend (3)
50% <= P < 62% Genügend (4)
0% <= P < 50% Nicht Genügend (5)To successfully complete the course, you need to achieve
* at least 50% of the points on the written exams (i.e., the points on the exams are summed up and you need to achieve at least 50% of the maximum number of points achievable), AND
* at least 50% of the points on the pen & paper exercises, AND
* at least 50% of the points on the programming assignments and their presentation.Attendance of the lecture parts of the course is voluntary but highly recommended. Attendance of the pen & paper exercise, the programming assignment presentations, and the written exams is compulsory to pass the course.
50% Written exams
25% Programming exercises
25% Pen & paper exercisesIn particular, let P = Average weighted percentage on the written exams, the programming exercises, and the pen & paper exercises. Then your grade (if you fulfill the passing criteria) is given as:90% <= P <= 100% Sehr Gut (1)
77% <= P < 90% Gut (2)
62% <= P < 77% Befriedigend (3)
50% <= P < 62% Genügend (4)
0% <= P < 50% Nicht Genügend (5)To successfully complete the course, you need to achieve
* at least 50% of the points on the written exams (i.e., the points on the exams are summed up and you need to achieve at least 50% of the maximum number of points achievable), AND
* at least 50% of the points on the pen & paper exercises, AND
* at least 50% of the points on the programming assignments and their presentation.Attendance of the lecture parts of the course is voluntary but highly recommended. Attendance of the pen & paper exercise, the programming assignment presentations, and the written exams is compulsory to pass the course.
Prüfungsstoff
The presented topics in the lecture (according to slides + exercises). Referenced Literature (as indicated in detail on the lecture slides).
Literatur
* Christopher Bishop, 2006, "Pattern Recognition and Machine Learning", Springer; available online: https://www.microsoft.com/en-us/research/publication/pattern-recognition-machine-learning/* Trevor Hastie, Robert Tibshirani, Jerome Friedman, 2009, "The Elements of Statistical Learning: Data Mining, Inference, and Prediction", Springer; available online: https://web.stanford.edu/~hastie/ElemStatLearn/* Tom Mitchell, 1997, "Machine Learning", McGraw Hill* Shai Shalev-Shwartz and Shai Ben-David, 2014, "Understanding Machine Learning: From Theory to Algorithms", Cambridge University Press; available online: https://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/
Zuordnung im Vorlesungsverzeichnis
Letzte Änderung: Di 21.10.2025 13:25
Upon successful participation in the course, students will be able to:
* Understand the theoretical foundations of machine learning.
* Design and implement basic machine learning pipelines.
* Apply linear models for regression and classification tasks.
* Evaluate and select models using appropriate validation techniques.
* Use clustering and dimensionality reduction techniques for data exploration and visualization.
* Understand the practical and theoretical foundations of advanced machine learning approaches such as kernels, neural networks, and probabilistic modeling. Implement these approaches and apply them to real-world problems.Lecture Contents:
* Introduction to Machine Learning:
- What is Machine Learning? Overview of key concepts and applications.
- Basic Machine Learning pipelines: From data preprocessing to model evaluation.
* Linear Models:
- Linear models for regression: Ordinary Least Squares, Ridge, and Lasso regression.
- Linear models for classification: Perceptrons, Support Vector Machines.
* Model Selection:
- Model validation: Cross-validation
- Model selection: Bias-variance tradeoff, hyperparameter tuning.
* Advanced Topics:
- Kernels: Basics, kernel trick
- Kernelized models: Support Vector Machines, Kernelized Regression
- Neural networks: Basics of feedforward networks and backpropagation. Techniques for improving generalization.
- Dimensionality reduction: PCA, Auto-encoders, and t-SNE.
- Probabilistic modeling: Bayesian inference, decision theory, graphical models, logistic regression.Method:
This course combines theoretical lectures with hands-on learning through:
Pen & Paper Exercises: Develop problem-solving skills by working through theoretical exercises.
Programming Assignments: Gain practical experience by implementing machine learning algorithms in Python.
Presentations: Enhance communication skills by presenting and discussing your pen & paper exercise solutions and programming assignment’s solutions with peers.